Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the full behavioral disclosure. It accurately conveys that rows are filtered with an OR condition on the given column and are returned in the order of the values provided. However, it does not address edge cases (e.g., no matches, duplicate matches) or the exact return structure beyond 'rows'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, well-structured sentence that front-loads the core behavior and uses a dash to append the use case. No redundant words; every part contributes to understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description does not explain the output format, which is critical given there is no output schema. The title mentions 'Compare rows side by side', but the description only says it returns rows, leaving uncertainty about whether the output is formatted for comparison. It also omits any mention of the maximum number of values (10) or behavior when no rows match.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description clarifies that 'column' is the key to filter on and that 'values' are the set to match against ('any of the given values'), implying an OR condition. It also explains that the order of values determines the output order, which is not evident from the schema alone. This adds meaningful semantics beyond the parameter names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb (returns), a resource (rows of the HardFM dataset), and the filtering condition (column matches any of the given values), along with ordering. It also notes the intended use case ('for X vs Y questions'), which distinguishes it from sibling tools like dataset_search or dataset_stats.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'for X vs Y questions' provides a clear use context, but it does not explicitly mention alternatives or when not to use this tool. No sibling tools are referenced, so an agent must infer that this is for comparison rather than general search or statistics.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.